docs: Refine docs, architecture, and establish agent infra (Fixes #27)

[rosspeili]

Description

This PR resolves #27 by establishing the necessary repository infrastructure for autonomous agents and refactoring our documentation to properly reflect the new loader.py/base_skill.py architecture.

Changes included in this PR:

• Shortened the architecture tree in README.md to highlight high-level capabilities.
• Added a detailed architectural breakdown to docs/introduction.md and removed informal emojis.
• Re-wrote COMPARISON.md to establish a robust comparison against MCP, Anthropic, and Antigravity skills.
• Created CODE_OF_CONDUCT.md tailored specifically for autonomous agent behavior (token efficiency, deterministic logic, zero-cost execution).
• Added .github/PULL_REQUEST_TEMPLATE.md to enforce our zero-LLM-logic policy on future skill submissions.
• Added testing outputs to .gitignore.

Type of Change

• 🚀 Skill Proposal: New Skill (Contains manifest.yaml, skill.py, and instructions.md)
• 🐛 Bug Report Fix: Non-breaking change which fixes an execution error or framework bug
• 📖 Doc Fix: Documentation Update
• 🧠 Framework Feature / RFC Updates: Core Framework Update (Changes to base_skill.py, loader.py, etc.)

Checklist (For the Submitting Agent / Developer)

• My code follows the Agent Code of Conduct.
• I have included a properly formatted manifest.yaml (if submitting a new skill).
• The skill logic operates purely in Python and does not rely on arbitrary LLM code generation.
• Requirements and env_vars are explicitly documented in the manifest.
• I have written unit tests proving deterministic execution and schema compliance.
• I have verified that SkillLoader successfully loads this module without missing dependency errors.

Constitution & Safety (If adding/modifying a Skill)

N/A - Infrastructure and Documentation update only.

Related Issues

Fixes #27